Nonvolatile Memory Read Reclaim via Read Count Assignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The high degree of integration in semiconductor storage devices leads to reliability issues due to increased read disturbances, which can damage data stored in these devices, necessitating a method to improve data reliability.
Innovation Solution
A storage device with a nonvolatile memory and a controller that performs a read reclaim operation by counting read operations and assigning data locations based on read counts, attributing read disturbances to valid data groups, and transferring data to minimize the impact of read disturbances.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the storage device operates at high integration density, then manufacturing cost is reduced and storage capacity is increased, but read disturbance increases causing data damage and reliability degradation
Solution Approach 1:
The controller proactively identifies data groups that have accumulated read disturbances exceeding a threshold value before actual data damage occurs. By performing read reclaim operations on these identified data groups, the system restores data to fresh memory blocks in advance, preventing reliability degradation from read disturbances.
Solution Approach 2:
The system continuously monitors and counts the number of read operations performed on each memory block. This feedback information is used to determine when data groups have accumulated sufficient read disturbances to trigger a read reclaim operation, enabling dynamic adaptation to actual usage patterns and disturbance accumulation.
2Reliability
If read reclaim operations are performed frequently to mitigate read disturbance, then data reliability is improved, but device complexity and operational overhead increase
Solution Approach 1:
The system uses a read count threshold parameter to control when read reclaim operations are triggered. By adjusting this threshold, the system can balance between performing reclaim operations frequently enough to maintain reliability while avoiding excessive operations that would increase complexity and overhead. The threshold provides a simple, configurable control mechanism.
Solution Approach 2:
The memory device is divided into multiple memory blocks that can be independently managed. The controller tracks read counts for each block separately and performs read reclaim operations on specific blocks that exceed the threshold, rather than universally reclaiming data from all blocks. This segmentation allows selective intervention only where needed.
Data Source
AI summary
A storage device includes a nonvolatile memory device and a controller. The nonvolatile memory device includes a plurality of memory blocks, each of which includes string selection transistors connected to a plurality of string selection lines, ground selection transistors connected to a plurality of ground selection lines, and memory cells connected to a plurality of word lines. The controller reads valid data groups of a first memory block and writes the read valid data groups in a second memory block, during a read reclaim operation. The controller assigns locations of the second memory block, at which the valid data groups are written, based on read counts of the valid data groups.